Google Gemini
Google Gemini API pricing calculator
Use one workload baseline to estimate monthly spend across every tracked Google Gemini model — input, cached-input, and output tokens included. Rank Google Gemini against 10 other providers on the same traffic pattern.
Updated
Google Gemini models · same workload baseline · last update: Wednesday 7th October 2026
Calculate my API costRelated: Openai vs Gemini · Claude vs Gemini · Cheapest Llm Api · Methodology
Calculator
Explore Google Gemini pricing for your workload
This estimate excludes cache storage and grounding/tool charges. Check the model, mode and context tier before budgeting.
Step 1
Review your assumptions
These are estimates, not measured usage. Edit the inputs or choose a preset.
Edit assumptions · 50,000 requests/month · 800 tokens/request · 82% input · 55% of input cached
50K requests / mo
800 tokens avg
Per request: 656 in · 144 out · 361 cached
Step 2
Lowest estimated cost
Top 4 models for this workload (unreviewed and conditional tariffs excluded)
General intelligence is not a task-specific quality guarantee. Test shortlisted models on your own examples. Source reviewed — exact offer checked on its provider page. Needs review — missing, stale or conflicting evidence; excluded from default recommendations. Estimates cover input/cache-read/output tokens only. Cache writes, storage, tools, search fees, taxes and unconfigured billing conditions are additional. Include billed reasoning tokens in your output estimate.
Selected model: cost breakdown
Estimate
Gemini 3.8 Flash (standard)
Google Gemini · focus model for this workload
Estimated monthly cost (USD)
$39.42
Based on: 50K requests · 656 input tokens/request · 144 output tokens/request · 55% of input from cache
Token costs only. Tool calls, search, storage, regional pricing, commitment discounts, and taxes may be excluded.
Explore all priced models
Step 3
Google Gemini models
6 models · Google Gemini
Estimated monthly cost
$39.42
How costs are calculated
Prices from ai-provider-pricing-validated.json, validated Wednesday 7th October 2026. Confirm on official provider pages before billing decisions. Dataset contains 95 offer records, including archived entries and offers that require additional billing inputs or price evidence. Only reviewed offers appear in this calculator. See excluded offers and reasons
Model Cost Comparison · Built by Lazige · Methodology
How we calculate cost
Monthly estimate = (input tokens × input $/MTok) + (cached tokens × cached $/MTok when published) + (output tokens × output $/MTok), scaled to your message volume. See the methodology for validation sources and update cadence.
Understanding Gemini API token costs
Snapshot validation: . These are the calculator’s dated rates, not a new price verification. Confirm current rates and availability with the provider.
What this estimate excludes
Gemini rates vary by model, modality, context tier and Standard or Batch mode. Output charges can include thinking tokens; measure billable usage rather than visible reply length alone.
Cached-input rates and cache-storage charges are separate. Storage depends on token volume and retention time. A cache ratio is an assumption: implicit caching discounts require actual cache hits.
Google Search grounding has additional, model-dependent charges. For models billed per search query, one user request can produce multiple billable queries. Check applicable allowances in the official pricing table.
Billing documentation checked September 23, 2026: Official Gemini API pricing · Gemini context caching.
Tracked token rates
| Model / tier | Input / MTok | Cached / MTok | Output / MTok | Evidence |
|---|---|---|---|---|
| Gemini 3.8 Flash (standard) | $0.75 | $0.075 | $3.75 | Provider source Primary source reviewed for stated scope Reviewed 2026-10-07T06:03:17.244Z Paid standard text rates through 2026-12-31; rates double 2027-01-01. Cache storage ($0.50/M token-hours), grounding and other tools excluded. |
| Gemini 2.5 Pro (standard) | $1.25 | $0.125 | $10 | Provider source Primary source reviewed for stated scope Reviewed 2026-10-07T06:03:17.244Z Gemini Developer API paid text standard, input at most 200000 tokens/request. Output includes thinking. Cache storage and grounding/search charges excluded; Pro above 200K uses a higher tariff. |
| Gemini 2.5 Pro (batch) | $0.625 | $0.125 | $5 | Provider source Primary source reviewed for stated scope Reviewed 2026-10-07T06:03:17.244Z Gemini Developer API paid text batch, input at most 200000 tokens/request. Output includes thinking. Cache storage and grounding/search charges excluded; Pro above 200K uses a higher tariff. |
| Gemini 2.5 Flash (standard) | $0.3 | $0.03 | $2.5 | Provider source Primary source reviewed for stated scope Reviewed 2026-10-07T06:03:17.244Z Gemini Developer API paid text standard, input at most 1000000 tokens/request. Output includes thinking. Cache storage and grounding/search charges excluded; Pro above 200K uses a higher tariff. |
| Gemini 2.5 Flash-Lite (standard) | $0.1 | $0.01 | $0.4 | Provider source Primary source reviewed for stated scope Reviewed 2026-10-07T06:03:17.244Z Gemini Developer API paid text standard, input at most 1000000 tokens/request. Output includes thinking. Cache storage and grounding/search charges excluded; Pro above 200K uses a higher tariff. |
| Gemini 2.5 Flash-Lite (batch) | $0.05 | $0.01 | $0.2 | Provider source Primary source reviewed for stated scope Reviewed 2026-10-07T06:03:17.244Z Gemini Developer API paid text batch, input at most 1000000 tokens/request. Output includes thinking. Cache storage and grounding/search charges excluded; Pro above 200K uses a higher tariff. |
| Gemini 2.0 Flash (standard) | $0.075 | $0.0187 | $0.3 | Provider source Not cross-checked Reviewed not established Gemini Developer API model shut down 2026-06-01, including standard and batch offers. |
| Gemini 2.0 Flash (batch) | $0.05 | $0.025 | $0.2 | Provider source Not cross-checked Reviewed not established Gemini Developer API model shut down 2026-06-01, including standard and batch offers. |
| Gemini 2.0 Flash-Lite (standard) | $0.075 | Not listed | $0.3 | Provider source Not cross-checked Reviewed not established Gemini Developer API model shut down 2026-06-01, including standard and batch offers. |
| Gemini 2.0 Flash-Lite (batch) | $0.0375 | Not listed | $0.15 | Provider source Not cross-checked Reviewed not established Gemini Developer API model shut down 2026-06-01, including standard and batch offers. |
Worked token-only example
For Gemini 3.8 Flash (standard), assume 1,000 requests with 1,000 uncached input tokens and 250 output tokens each: 1 million input tokens + 0.25 million output tokens. Using this snapshot, $0.75 + (0.25 × $3.75) = $1.6875 in token charges. This illustrative workload is separate from the editable calculator above. This estimate excludes cache storage and grounding/tool charges. Check the model, mode and context tier before budgeting.
Provider scenarios
Workloads teams model on Google Gemini
Illustrative patterns for Google Gemini pricing — start from a preset, then refine tokens from your usage dashboard.
“Estimate support traffic on Google Gemini using measured input and output tokens; apply cache discounts only when supported.”
“RAG on Google Gemini should use the retrieval preset so repeated context is priced at the cached-input rate when available.”
“Coding assistants on Google Gemini need longer average tokens — the code preset is a better planning baseline than chat defaults.”
“Before shipping agents on Google Gemini, compare monthly cost at your expected tool-call volume — not a single-turn demo.”